Title :
Knowledge-increasable model and its algorithm
Author :
Yingjian, Qi ; Jianyu, Li ; Jiali, Zhao ; Siwei, Luo
Author_Institution :
Dept. of Comput. Sci. & Technol., Northern Jiaotong Univ., Beijing, China
Abstract :
A knowledge-increasable system (KIS) is a kind of combined artificial neural network. This conception is proposed to accomplish inheritance and accumulation of the sub-network without destroying the existing function. We put up a model to perform the KIS, and compare this model with the popular Mixture of Experts (ME) model. We classify the model by three different situations and give the corresponding algorithm. We introduce future work
Keywords :
knowledge engineering; learning (artificial intelligence); neural nets; Mixture of Experts model; combined artificial neural network; ensemble learning; knowledge accumulation; knowledge inheritance; knowledge-increasable model; sub-network inheritance; Artificial neural networks; Computer architecture; Computer science; Decision trees; Iterative algorithms; Jacobian matrices; Mars; Neural networks; Partial response channels; Spline;
Conference_Titel :
Info-tech and Info-net, 2001. Proceedings. ICII 2001 - Beijing. 2001 International Conferences on
Conference_Location :
Beijing
Print_ISBN :
0-7803-7010-4
DOI :
10.1109/ICII.2001.983041
